CN108416791B - Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method - Google Patents
Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method Download PDFInfo
- Publication number
- CN108416791B CN108416791B CN201810170162.8A CN201810170162A CN108416791B CN 108416791 B CN108416791 B CN 108416791B CN 201810170162 A CN201810170162 A CN 201810170162A CN 108416791 B CN108416791 B CN 108416791B
- Authority
- CN
- China
- Prior art keywords
- camera
- moving platform
- identification area
- parallel mechanism
- calibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007246 mechanism Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 238000003384 imaging method Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 16
- 239000002245 particle Substances 0.000 claims description 11
- 238000005260 corrosion Methods 0.000 claims description 10
- 230000007797 corrosion Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 13
- 239000011664 nicotinic acid Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a binocular vision-based parallel mechanism moving platform pose monitoring and tracking method, which comprises the steps of collecting pose images of a moving platform circular identification area shot by a left camera and a right camera at different angles, constructing an edge search model by means of image recognition and feature extraction technology, extracting a plurality of points with limited edges of a moving platform, and respectively carrying out ellipse fitting on the edge points of the moving platform identification area by adopting a least square method and a meta-heuristic intelligent algorithm to obtain a central pixel coordinate value of the moving platform identification area; based on a camera calibration tool box and a calibration plate with known size, calibrating parameters of a monocular camera to obtain a binocular stereo matching algorithm, and realizing binocular calibration; based on the camera imaging principle relationship, the relationship between the internal and external parameters of the left camera and the right camera, the pixel coordinate of the central point of the identification area of the movable platform and the world coordinate is deduced, the real-time three-dimensional coordinate of the central point of the identification area of the movable platform is reconstructed, and the real-time monitoring and tracking of the pose of the movable platform are realized. The invention has the advantages of high measurement precision, error reduction and the like.
Description
Technical Field
The invention relates to the field of pose monitoring and tracking, in particular to a binocular vision parallel mechanism moving platform pose monitoring and tracking method.
Background
The parallel mechanism consists of a fixed platform, a movable platform and a plurality of intermediate branched chains, and has the advantages of large specific rigidity, compact structure, strong bearing capacity, good stability and the like. However, the motion of the movable platform of the parallel mechanism is determined by the motion of a plurality of intermediate branched chains, the coupling degree is high, the control is complex, and the accurate measurement of the pose of the movable platform at the output end has important significance for the high-performance control of the whole parallel mechanism. The traditional measuring method comprises contact measurement, monocular measurement, binocular single-point measurement and the like, wherein the contact measurement requires that measuring equipment moves along with a mechanism and is greatly influenced by the movement, and meanwhile, the measuring equipment tends to change the mass distribution of the mechanism to influence the normal operation of the mechanism; monocular measurement utilizes a camera to identify the motion of a tracking mechanism, the uncertainty in direction measurement is large, and the depth recovery is difficult; the binocular single-point measurement is based on the fact that the two cameras simultaneously recognize the movement of the single mark point on the mechanism, and is limited by the environment, information is easily lost, and the tracking effect is influenced.
Disclosure of Invention
The invention aims to provide a binocular vision-based parallel mechanism moving platform pose monitoring and tracking method which is high in measurement accuracy and capable of reducing errors.
In order to realize the purpose, the following technical scheme is adopted: the method comprises image acquisition equipment, namely a high-definition camera, a computer and a parallel mechanism, wherein a moving platform of the parallel mechanism is not required to be circular, and a camera marker attached to the central point of the moving platform is required to be circular or elliptical;
the method comprises the following steps:
step 1, calibrating internal and external parameters of a left camera and a right camera through a binocular camera and a known size calibration board based on a camera imaging principle relation and a camera monocular calibration toolbox;
step 2, image acquisition is carried out on the parallel mechanism, and a moving platform identification area is extracted through component distribution extraction, threshold segmentation and corrosion treatment of a specific straight line R, G, B;
step 3, simplifying an image matrix, establishing an edge search model, and performing edge search on the identification area of the movable platform to obtain the pixel coordinate value of an edge point;
step 4, respectively performing edge point ellipse fitting by adopting a least square method and a meta-heuristic intelligent algorithm to obtain a central pixel coordinate value of the identification area of the movable platform;
step 5, based on a camera imaging principle, realizing the reconstruction of the three-dimensional coordinates of the central point of the identification area of the movable platform of the parallel mechanism, and further obtaining the pose of the movable platform of the parallel mechanism;
and 6, analyzing, displaying and recording the pose of the movable platform in real time to achieve the purpose of monitoring and tracking the motion state of the movable platform in real time.
Further, the specific content of step 1 is as follows:
1-1, fixing the left camera and the right camera, keeping the relative positions unchanged, and calibrating the internal and external parameters of the left camera and the right camera again after the relative positions change;
1-2, using a black and white checkerboard with known dimensions as a calibration board, and selecting a plurality of groups of images of the calibration board, which are shot by a left camera and a right camera at the same time and under different poses;
1-3, based on a Zhang calibration method, obtaining monocular calibration results of a left camera and a right camera respectively by means of a monocular calibration algorithm in an existing camera calibration tool box;
and 1-4, deepening to obtain a stereo matching algorithm of the left camera and the right camera based on a monocular calibration algorithm, and outputting internal parameters of the left camera and external parameters taking a light spot of the left camera as a reference.
Further, the specific content of step 2 is as follows:
2-1, selecting a specific straight line passing through the identification area according to the position of the identification area of the movable platform in the image, and extracting R, G, B component distribution on the straight line;
2-2, setting a threshold value R-G-N according to R, G, B component distribution of a specific straight line1、R-B＝N2Performing image segmentation processing to process the picture into a black and white picture;
and 2-3, carrying out corrosion treatment on the obtained image, removing interference points in a non-target area and filling holes in the target area, wherein the corrosion times are set according to the effect.
Further, the specific content of step 3 is as follows:
3-1, mapping the image matrix into a 0-1 matrix by adopting binarization processing to simplify the image matrix;
3-2, establishing an edge search model with a point pixel value of 0 and the sum of the pixels of the four adjacent pixel points not less than 1, traversing each pixel point of the image from top to bottom, from left to right, and recording the coordinate value of the edge point pixel.
Further, the specific content of step 4 is as follows:
4-1, obtaining a general elliptic equation after rotating and translating through a standard elliptic equation, randomly selecting a plurality of points on the circumference of a theoretical ellipse based on Monte Carlo random numbers, and establishing a distance model between an edge acquisition point and the closest point of the plurality of points on the theoretical ellipse;
4-2, determining the major axis a, the minor axis b and the center pixel coordinate (x) of a general elliptic equation by taking the distance sum minimum as an optimization functionc,yc) Five variables of the rotation angle theta are optimized parameters;
4-3, respectively carrying out ellipse edge fitting by adopting a least square method and three kinds of meta-heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight particle swarm algorithm, so as to obtain the coordinate value of the central pixel of the identification area of the mobile platform.
Further, the specific content of step 5 is as follows:
5-1, based on a camera imaging principle, obtaining a relation among an image coordinate system, a camera coordinate system and a world coordinate system, and further obtaining a relation among left and right camera internal and external parameters, a moving platform identification area central point pixel coordinate and a world coordinate;
and 5-2, reconstructing world coordinate values of the left camera, the right camera, the inside camera, the outside camera and the inside camera, the outside camera and the inside camera.
The working process is roughly as follows:
a round identification area of a parallel mechanism moving platform is extracted by means of threshold segmentation, coordinate values of edge pixel points of the identification area of the moving platform are extracted through an edge search model, ellipse fitting is carried out on the basis of a least square method and three meta-heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight strategy particle swarm algorithm, so as to obtain the position of a pixel at the center point of the identification area of the moving platform, the motion pose of the parallel mechanism moving platform is measured in real time in a binocular vision non-contact mode from the perspective of bionic binocular vision, and a set of intelligent system is developed with the purposes of monitoring and tracking the motion pose of the parallel mechanism moving platform in real time and ensuring high-precision motion of the mechanism.
Compared with the prior art, the method has the following advantages:
1. and non-contact measurement is adopted, so that no interference or influence is generated on the motion of the parallel mechanism.
2. From the bionic dual-purpose angle, binocular stereo recognition is carried out, depth information can be restored, and the measuring result is more accurate and reliable than monocular measurement.
3. The central point of the identification area of the movable platform is subjected to threshold segmentation and edge extraction, the red circular identification edge of the identification area is identified and obtained by combining an ellipse fitting method, and compared with the method for directly measuring the central point of the identification area, the method can reduce errors caused by inaccurate measurement.
4. The least square method and three kinds of meta-heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight strategy particle swarm algorithm are adopted to fit the ellipse, so that the adaptability of software is improved, and the extraction of the central point of the identification area is more accurate.
5. The functions of calibrating the internal and external parameters of the left camera and the right camera, extracting the central pixel of the identification area of the movable platform, monitoring the pose of the movable platform and tracking are integrated and embedded into one software, and a one-stop basis is provided for the high-performance control of the parallel mechanism.
Drawings
FIG. 1 is a general flow diagram of the process of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
as shown in fig. 1, the method of the present invention includes image acquisition devices, i.e. a high definition video camera, a computer, and a parallel mechanism, wherein the moving platform of the parallel mechanism does not need to be circular, and the camera marker attached to the center point of the moving platform needs to be circular or elliptical;
the method comprises the following steps:
step 1, calibrating internal and external parameters of a left camera and a right camera through a binocular camera and a known size calibration board based on a camera imaging principle relation and a camera monocular calibration toolbox;
1-1, fixing the left camera and the right camera, keeping the relative positions unchanged, and calibrating the internal and external parameters of the left camera and the right camera again after the relative positions change;
1-2, using a black and white checkerboard with known dimensions as a calibration board, and selecting a plurality of groups of images of the calibration board, which are shot by a left camera and a right camera at the same time and under different poses;
1-3, based on a Zhang calibration method, obtaining monocular calibration results of a left camera and a right camera respectively by means of a monocular calibration algorithm in an existing camera calibration tool box;
and 1-4, deepening to obtain a stereo matching algorithm of the left camera and the right camera based on a monocular calibration algorithm, and outputting internal parameters of the left camera and external parameters taking a light spot of the left camera as a reference.
Step 2, image acquisition is carried out on the parallel mechanism, and a moving platform identification area is extracted through component distribution extraction, threshold segmentation and corrosion treatment of a specific straight line R, G, B;
2-1, selecting a specific straight line passing through the identification area according to the position of the identification area of the movable platform in the image, and extracting R, G, B component distribution on the straight line;
2-2, setting a threshold value R-G-N according to R, G, B component distribution of a specific straight line1、R-B＝N2Performing image segmentation processing to process the picture into a black and white picture;
and 2-3, carrying out corrosion treatment on the obtained image, removing interference points in a non-target area and filling holes in the target area, wherein the corrosion times are set according to the effect.
Step 3, simplifying an image matrix, establishing an edge search model, and performing edge search on the identification area of the movable platform to obtain the pixel coordinate value of an edge point;
3-1, mapping the image matrix into a 0-1 matrix by adopting binarization processing to simplify the image matrix;
3-2, establishing an edge search model with a point pixel value of 0 and the sum of the pixels of the four adjacent pixel points not less than 1, traversing each pixel point of the image from top to bottom, from left to right, and recording the coordinate value of the edge point pixel.
Step 4, respectively performing edge point ellipse fitting by adopting a least square method and a meta-heuristic intelligent algorithm to obtain a central pixel coordinate value of the identification area of the movable platform;
4-1, obtaining a general elliptic equation after rotating and translating through a standard elliptic equation, randomly selecting a plurality of points on the circumference of a theoretical ellipse based on Monte Carlo random numbers, and establishing a distance model between an edge acquisition point and the closest point of the plurality of points on the theoretical ellipse;
4-2, determining the major axis a, the minor axis b and the center pixel coordinate (x) of a general elliptic equation by taking the distance sum minimum as an optimization functionc,yc) Five variables of the rotation angle theta are optimized parameters;
4-3, respectively carrying out ellipse edge fitting by adopting a least square method and three kinds of meta-heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight particle swarm algorithm, so as to obtain the coordinate value of the central pixel of the identification area of the mobile platform.
Step 5, based on a camera imaging principle, realizing the reconstruction of the three-dimensional coordinates of the central point of the identification area of the movable platform of the parallel mechanism, and further obtaining the pose of the movable platform of the parallel mechanism;
5-1, based on a camera imaging principle, obtaining a relation among an image coordinate system, a camera coordinate system and a world coordinate system, and further obtaining a relation among left and right camera internal and external parameters, a moving platform identification area central point pixel coordinate and a world coordinate;
and 5-2, reconstructing world coordinate values of the left camera, the right camera, the inside camera, the outside camera and the inside camera, the outside camera and the inside camera.
And 6, analyzing, displaying and recording the pose of the movable platform in real time to achieve the purpose of monitoring and tracking the motion state of the movable platform in real time.
Example 1:
in this embodiment, the internal and external parameters of the two cameras are calibrated, and the two cameras are fixed on the rack convenient for monitoring the parallel mechanism.
The method comprises the steps of taking a black and white board with each small square being 25mm multiplied by 25mm as a calibration board, simultaneously shooting by two cameras, acquiring images of a series of left and right cameras of the calibration board in different positions, sequentially carrying out left camera calibration and right camera calibration based on a Zhang calibration method, correspondingly obtaining calibration results of an angular point extraction error, an internal reference matrix, radial distortion, tangential distortion and the like of the left camera and the right camera, and finally carrying out left and right stereo calibration to obtain calibration results of an angular point extraction error of an image of a corresponding pose of two cameras, an internal reference matrix, radial distortion, tangential distortion, a rotation matrix, a translation matrix and the like of the two cameras. Once the relative position of the camera is fixed, it is not allowed to change, otherwise it needs to be calibrated again.
Under the initial static condition, acquiring an initial pose image of the parallel mechanism, selecting a specific straight line passing through the identification region, extracting R, G, B component distribution on the specific straight line, setting thresholds R-G (equal to N1) and R-B (equal to N2) to segment the initial pose image of the parallel mechanism, processing the picture into a black-and-white picture (the identification region is black), carrying out corrosion treatment, improving the segmentation effect of the image of the identification region, removing interference points of a non-target region and filling holes in the target region.
Aiming at a parallel mechanism, shooting an image in real time through a camera, carrying out image preprocessing according to a set threshold value, establishing an edge search model with a point pixel value of 0 and the sum of the pixels of four adjacent pixel points of not less than 1 in real time, traversing each pixel point of the image from top to bottom, from left to right, recording the edge point pixel coordinate value of an identification area, respectively applying a least square method and three element heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight strategy, carrying out edge point ellipse fitting, respectively obtaining the central pixel coordinate value of an identification area of a moving platform, accumulating and averaging the fitting central points to be used as the real-time central pixel coordinate value of the identification area of the moving platform, and obtaining the relation among an image coordinate system, a camera coordinate system and a world coordinate system based on the camera imaging principle, and obtaining the inside and outside parameters of the left camera and the right camera and the moving platform identification area through the extraction of image characteristics And on the basis of the pixel coordinate of the central point, the real-time three-dimensional coordinate of the central point of the identification area of the movable platform of the parallel mechanism is obtained.
The pose of the movable platform is analyzed, displayed and recorded in real time, and the purpose of monitoring and tracking the motion state of the movable platform in real time is achieved.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solution of the present invention by those skilled in the art should fall within the protection scope defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (6)
1. A binocular vision-based parallel mechanism moving platform pose monitoring and tracking method is characterized in that the method comprises image acquisition equipment, namely a high-definition video camera, a computer and a parallel mechanism, the moving platform of the parallel mechanism does not need to be circular, and a camera marker attached to the central point of the moving platform needs to be circular or elliptical;
the method comprises the following steps:
step 1, calibrating internal and external parameters of a left camera and a right camera through a binocular camera and a known size calibration board based on a camera imaging principle relation and a camera monocular calibration toolbox;
step 2, image acquisition is carried out on the parallel mechanism, and a moving platform identification area is extracted through component distribution extraction, threshold segmentation and corrosion treatment of a specific straight line R, G, B;
step 3, simplifying an image matrix, establishing an edge search model, and performing edge search on the identification area of the movable platform to obtain the pixel coordinate value of an edge point;
step 4, respectively performing edge point ellipse fitting by adopting a least square method and a meta-heuristic intelligent algorithm to obtain a central pixel coordinate value of the identification area of the movable platform;
step 5, based on a camera imaging principle, realizing the reconstruction of the three-dimensional coordinates of the central point of the identification area of the movable platform of the parallel mechanism, and further obtaining the pose of the movable platform of the parallel mechanism;
and 6, analyzing, displaying and recording the pose of the movable platform in real time to achieve the purpose of monitoring and tracking the motion state of the movable platform in real time.
2. The binocular vision based parallel mechanism moving platform pose monitoring and tracking method according to claim 1, wherein the specific content of the step 1 is as follows:
1-1, fixing the left camera and the right camera, keeping the relative positions unchanged, and calibrating the internal and external parameters of the left camera and the right camera again after the relative positions change;
1-2, using a black and white checkerboard with known dimensions as a calibration board, and selecting a plurality of groups of images of the calibration board, which are shot by a left camera and a right camera at the same time and under different poses;
1-3, based on a Zhang calibration method, obtaining monocular calibration results of a left camera and a right camera respectively by means of a monocular calibration algorithm in an existing camera calibration tool box;
and 1-4, deepening to obtain a stereo matching algorithm of the left camera and the right camera based on a monocular calibration algorithm, and outputting internal parameters of the left camera and external parameters taking a light spot of the left camera as a reference.
3. The binocular vision based parallel mechanism moving platform pose monitoring and tracking method according to claim 1, wherein the specific content of the step 2 is as follows:
2-1, selecting a specific straight line passing through the identification area according to the position of the identification area of the movable platform in the image, and extracting R, G, B component distribution on the straight line;
2-2, setting a threshold value R-G-N according to R, G, B component distribution of a specific straight line1、R-B＝N2Performing image segmentation processing to process the picture into a black and white picture;
and 2-3, carrying out corrosion treatment on the obtained image, removing interference points in a non-target area and filling holes in the target area, wherein the corrosion times are set according to the effect.
4. The binocular vision based parallel mechanism moving platform pose monitoring and tracking method according to claim 1, wherein the specific content of the step 3 is as follows:
3-1, mapping the image matrix into a 0-1 matrix by adopting binarization processing to simplify the image matrix;
3-2, establishing an edge search model with a point pixel value of 0 and the sum of the pixels of the four adjacent pixel points not less than 1, traversing each pixel point of the image from top to bottom, from left to right, and recording the coordinate value of the edge point pixel.
5. The binocular vision based parallel mechanism moving platform pose monitoring and tracking method according to claim 1, wherein the specific content of the step 4 is as follows:
4-1, obtaining a general elliptic equation after rotating and translating through a standard elliptic equation, randomly selecting a plurality of points on the circumference of a theoretical ellipse based on Monte Carlo random numbers, and establishing a distance model between an edge acquisition point and the closest point of the plurality of points on the theoretical ellipse;
4-2, determining the major axis a, the minor axis b and the center pixel coordinate (x) of a general elliptic equation by taking the distance sum minimum as an optimization functionc,yc) Five variables of the rotation angle theta are optimized parameters;
4-3, respectively carrying out ellipse edge fitting by adopting a least square method and three kinds of meta-heuristic intelligent algorithms, namely a genetic algorithm, a self-adaptive weight particle swarm algorithm and a random weight particle swarm algorithm, so as to obtain the coordinate value of the central pixel of the identification area of the mobile platform.
6. The binocular vision based parallel mechanism moving platform pose monitoring and tracking method according to claim 1, wherein the specific content of the step 5 is as follows:
5-1, based on a camera imaging principle, obtaining a relation among an image coordinate system, a camera coordinate system and a world coordinate system, and further obtaining a relation among left and right camera internal and external parameters, a moving platform identification area central point pixel coordinate and a world coordinate;
and 5-2, reconstructing world coordinate values of the left camera, the right camera, the inside camera, the outside camera and the inside camera, the outside camera and the inside camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170162.8A CN108416791B (en) | 2018-03-01 | 2018-03-01 | Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170162.8A CN108416791B (en) | 2018-03-01 | 2018-03-01 | Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108416791A CN108416791A (en) | 2018-08-17 |
| CN108416791B true CN108416791B (en) | 2021-07-23 |
Family
ID=63129635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810170162.8A Active CN108416791B (en) | 2018-03-01 | 2018-03-01 | Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416791B (en) |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109308693B (en) * | 2018-08-29 | 2023-01-24 | 北京航空航天大学 | Single-binocular vision system for target detection and pose measurement constructed by one PTZ camera |
| US10997760B2 (en) * | 2018-08-31 | 2021-05-04 | Snap Inc. | Augmented reality anthropomorphization system |
| CN111630851A (en) * | 2018-10-10 | 2020-09-04 | 深圳配天智能技术研究院有限公司 | Camera calibration device, system and method and device with storage function |
| CN111145248B (en) * | 2018-11-06 | 2023-06-27 | 北京地平线机器人技术研发有限公司 | Pose information determining method and device and electronic equipment |
| CN110268444A (en) * | 2019-02-26 | 2019-09-20 | 武汉资联虹康科技股份有限公司 | A kind of number of people posture tracing system for transcranial magnetic stimulation diagnosis and treatment |
| CN110175960B (en) * | 2019-05-21 | 2021-04-13 | Oppo广东移动通信有限公司 | Image correction method, image correction device, electronic device and storage medium |
| CN110363905B (en) * | 2019-07-31 | 2021-09-17 | 浪潮金融信息技术有限公司 | Vending machine detection area positioning and goods discharge detection method based on sliding rail |
| CN110570477B (en) * | 2019-08-28 | 2022-03-11 | 贝壳技术有限公司 | Method, device and storage medium for calibrating relative attitude of camera and rotating shaft |
| CN110415292A (en) * | 2019-09-02 | 2019-11-05 | 安徽建筑大学 | Movement attitude vision measurement method of ring identification and application thereof |
| CN112541950A (en) * | 2019-09-20 | 2021-03-23 | 杭州海康机器人技术有限公司 | Method and device for calibrating external parameter of depth camera |
| CN110827357B (en) * | 2019-09-30 | 2024-03-29 | 深圳市安思疆科技有限公司 | Combined pattern calibration plate and structured light camera parameter calibration method |
| CN110706289B (en) * | 2019-10-24 | 2022-09-30 | 中国科学技术大学 | Attitude measurement method and device |
| CN113052910B (en) * | 2019-12-27 | 2024-07-19 | 杭州海康机器人股份有限公司 | Calibration guiding method and camera device |
| CN111210413B (en) * | 2020-01-02 | 2023-10-03 | 北京机科国创轻量化科学研究院有限公司 | Pose detection method in movement process of wire feeding mechanism |
| CN113409236A (en) * | 2020-06-29 | 2021-09-17 | 华中科技大学 | Steel arch frame hinge hole detection method based on binocular vision and application thereof |
| CN112258582B (en) * | 2020-10-12 | 2022-11-08 | 武汉中海庭数据技术有限公司 | Camera attitude calibration method and device based on road scene recognition |
| CN112288808B (en) * | 2020-10-22 | 2024-06-14 | 扬州大学 | Visual-based diesel engine piston cylinder step hole diameter position measurement method |
| CN112381847B (en) * | 2020-10-27 | 2024-02-13 | 新拓三维技术(深圳)有限公司 | Pipeline end space pose measurement method and system |
| CN112581542B (en) * | 2020-12-24 | 2024-07-19 | 阿波罗智联(北京)科技有限公司 | Evaluation method, device and equipment for monocular calibration algorithm of automatic driving |
| CN112634377B (en) * | 2020-12-28 | 2024-08-13 | 深圳市杉川机器人有限公司 | Camera calibration method, terminal and computer readable storage medium of sweeping robot |
| CN112950669A (en) * | 2021-03-05 | 2021-06-11 | 深圳市华艺鑫电子有限公司 | System and method for identifying and measuring circular moving target based on state estimation |
| CN113516716B (en) * | 2021-07-16 | 2022-11-08 | 燕山大学 | Monocular vision pose measuring and adjusting method and system |
| CN116051629B (en) * | 2023-02-22 | 2023-11-07 | 常熟理工学院 | Autonomous navigation robot-oriented high-precision visual positioning method |
| CN116740183B (en) * | 2023-08-15 | 2023-11-07 | 浙江大学 | Double-view cabin pose adjusting method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102506757A (en) * | 2011-10-10 | 2012-06-20 | 南京航空航天大学 | Self-positioning method of binocular stereo measuring system in multiple-visual angle measurement |
| CN105066909A (en) * | 2015-09-01 | 2015-11-18 | 华中科技大学 | Hand-held multi-laser-stripe quick three-dimensional measuring method |
| CN106272437A (en) * | 2016-10-12 | 2017-01-04 | 吉林大学 | Device is asked in a kind of optimum visual field for parallel robot binocular visual positioning |
| CN107292927A (en) * | 2017-06-13 | 2017-10-24 | 厦门大学 | A kind of symmetric motion platform's position and pose measuring method based on binocular vision |
| CN107321969A (en) * | 2017-08-10 | 2017-11-07 | 安徽理工大学 | The wheeled removable heavily loaded foundry robot of omnidirectional |
| CN107545593A (en) * | 2017-10-19 | 2018-01-05 | 深圳大学 | The Fourier's lamination image space scaling method and device of vision auxiliary |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104315978B (en) * | 2014-11-10 | 2017-03-29 | 北京理工大学 | A kind of measuring method and device of pipeline end face center point |
| CN106296628B (en) * | 2015-05-11 | 2019-03-05 | 株式会社理光 | The method and apparatus for detecting abnormal case |
| CN106408609B (en) * | 2016-09-13 | 2019-05-31 | 江苏大学 | A kind of parallel institution end movement position and posture detection method based on binocular vision |
-
2018
- 2018-03-01 CN CN201810170162.8A patent/CN108416791B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102506757A (en) * | 2011-10-10 | 2012-06-20 | 南京航空航天大学 | Self-positioning method of binocular stereo measuring system in multiple-visual angle measurement |
| CN105066909A (en) * | 2015-09-01 | 2015-11-18 | 华中科技大学 | Hand-held multi-laser-stripe quick three-dimensional measuring method |
| CN106272437A (en) * | 2016-10-12 | 2017-01-04 | 吉林大学 | Device is asked in a kind of optimum visual field for parallel robot binocular visual positioning |
| CN107292927A (en) * | 2017-06-13 | 2017-10-24 | 厦门大学 | A kind of symmetric motion platform's position and pose measuring method based on binocular vision |
| CN107321969A (en) * | 2017-08-10 | 2017-11-07 | 安徽理工大学 | The wheeled removable heavily loaded foundry robot of omnidirectional |
| CN107545593A (en) * | 2017-10-19 | 2018-01-05 | 深圳大学 | The Fourier's lamination image space scaling method and device of vision auxiliary |
Non-Patent Citations (6)
| Title |
|---|
| A monocular vision system for online pose measurement of a 3RRR planar parallel manipulator;Hai Li等;《Journal of Intelligent & Robotic Systems》;20171031;第92卷;第3-17页 * |
| Chaos phenomenon and stability analysis of RU-RPR parallel mechanism with clearance and friction;Yulei Hou等;《Advances in Mechanical Engineering》;20180106;第10卷(第1期);第1-11页 * |
| Research on Structural Parameter Optimization of Binocular Vision Measuring System for Parallel Mechanism;Yubo Guo等;《2006 International Conference on Mechatronics and Automation》;20061231;第1131-1135页 * |
| 基于双目视觉的3-PRS并联机构末端位姿检测方法;赵俊伟等;《制造技术与机床》;20180131(第1期);第101-106页 * |
| 基于双目视觉的新型并联机构末端位姿检测;高国琴等;《测控技术》;20161130;第35卷(第11期);第14-17、21页 * |
| 基于视觉的并联机构位置检测系统的研究;张小康;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150215(第02期);第I140-515页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108416791A (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416791B (en) | Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method | |
| WO2021004312A1 (en) | Intelligent vehicle trajectory measurement method based on binocular stereo vision system | |
| CA2961921C (en) | Camera calibration method using a calibration target | |
| CN105894499A (en) | Binocular-vision-based rapid detection method for three-dimensional information of space object | |
| US20170124693A1 (en) | Pose Estimation using Sensors | |
| CN109801333B (en) | Volume measurement method, device and system and computing equipment | |
| CN108955718A (en) | A kind of visual odometry and its localization method, robot and storage medium | |
| Pedersen et al. | Camera calibration for underwater 3D reconstruction based on ray tracing using Snell's law | |
| CN105043350A (en) | Binocular vision measuring method | |
| CN108519102B (en) | Binocular vision mileage calculation method based on secondary projection | |
| CN106485735A (en) | Human body target recognition and tracking method based on stereovision technique | |
| García-Moreno et al. | LIDAR and panoramic camera extrinsic calibration approach using a pattern plane | |
| CN110648362B (en) | Binocular stereo vision badminton positioning identification and posture calculation method | |
| CN107084680A (en) | Target depth measuring method based on machine monocular vision | |
| Cvišić et al. | Recalibrating the KITTI dataset camera setup for improved odometry accuracy | |
| CN107885224A (en) | Unmanned plane barrier-avoiding method based on tri-item stereo vision | |
| CN103712604A (en) | Method and system for optically positioning multi-target three-dimensional space | |
| CN110597249A (en) | Robot and recharging positioning method and device thereof | |
| CN111243003A (en) | Vehicle-mounted binocular camera and method and device for detecting road height limiting rod | |
| CN110646231A (en) | Floor sweeping robot testing method and device | |
| CN107590444A (en) | Detection method, device and the storage medium of static-obstacle thing | |
| CN111798507A (en) | Power transmission line safety distance measuring method, computer equipment and storage medium | |
| CN111142514A (en) | Robot and obstacle avoidance method and device thereof | |
| US20190313082A1 (en) | Apparatus and method for measuring position of stereo camera | |
| CN111598956A (en) | Calibration method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| OL01 | Intention to license declared | ||
| OL01 | Intention to license declared |